Paper: Transformation from Discontinuous to Continuous Word Alignment Improves Translation Quality

ACL ID D14-1016
Title Transformation from Discontinuous to Continuous Word Alignment Improves Translation Quality
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

We present a novel approach to im- prove word alignment for statistical ma- chine translation (SMT). Conventional word alignment methods allow discontin- uous alignment, meaning that a source (or target) word links to several target (or source) words whose positions are dis- continuous. However, we cannot extrac- t phrase pairs from this kind of align- ments as they break the alignment con- sistency constraint. In this paper, we use a weighted vote method to transform dis- continuous word alignment to continuous alignment, which enables SMT system- s extract more phrase pairs. We carry out experiments on large scale Chinese- to-English and German-to-English trans- lation tasks. Experimental results show statistically significant improvements of BLEU score in both cases over the base- line ...